Skip to main content
Glama
Sign In
people-context

people-context

by JinyangWang27
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

semantic_search

Read-only

Search active people and safe interaction summaries by multilingual semantic similarity; run the local semantic reindex first to enable queries without model downloads.

Instructions

Search active people and safe interaction summaries by multilingual semantic similarity.

This optional local search requires an explicit pctx reindex --semantic first. It never downloads a model while serving a query and refuses to mix vectors from different model revisions.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "semantic_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindsNo
limitNo
queryYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.5.0
    • changedOutput schema / (root)
      Previous value: -{
-  "additionalProperties": true,
-  "title": "semantic_searchDictOutput",
-  "type": "object"
-}New value: +null
  2. First observedv1.1.1

TDQS

B3.3/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, and the description adds substantive behavior: it never downloads a model while serving a query, it refuses to mix vectors from different model revisions, and it only covers 'active' people. These are failure-mode disclosures an agent cannot get from structured fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The opening sentence is well front-loaded, but the second sentence is split awkwardly with a line break and the trailing fragment about refusing to mix model revisions reads as an afterthought rather than structured guidance. Nothing is bloated, but the layout is loose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and zero parameter documentation, the description should carry more weight. It covers the indexing prerequisite and model-version constraint well, but leaves what results look like and what `kinds` accepts entirely unspecified.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across three parameters. The description only implies that `query` is free-text and multilingual, and says nothing at all about what `kinds` filters or what `limit` controls, so the compensation the low coverage demands is missing.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource set — 'Search active people and safe interaction summaries' — plus the retrieval mode 'multilingual semantic similarity'. That distinguishes it from keyword-style siblings like search_people, though the alternative is not named directly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a hard precondition ('requires an explicit `pctx reindex --semantic` first') and marks the tool 'optional', which is real usage context. It does not say when to prefer this over search_people or the other lookup siblings, so the agent still has to infer the selection rule.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools